PyPI - docling-core - Versions diffs - 2.23.0__tar.gz → 2.23.2__tar.gz - Mend

docling-core 2.23.0tar.gz → 2.23.2tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of docling-core might be problematic. Click here for more details.

Files changed (68) hide show

{docling_core-2.23.0 → docling_core-2.23.2}/PKG-INFO RENAMED Viewed

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.23.0
+Version: 2.23.2
 Summary: A python library to define and validate data types in Docling.
-Home-page: https://ds4sd.github.io/
+Home-page: https://github.com/docling-project
 License: MIT
 Keywords: docling,discovery,etl,information retrieval,analytics,database,database schema,schema,JSON
 Author: Cesar Berrospi Ramis
@@ -38,7 +38,7 @@ Requires-Dist: tabulate (>=0.9.0,<0.10.0)
 Requires-Dist: transformers (>=4.34.0,<5.0.0) ; extra == "chunking"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Requires-Dist: typing-extensions (>=4.12.2,<5.0.0)
-Project-URL: Repository, https://github.com/DS4SD/docling-core
+Project-URL: Repository, https://github.com/docling-project/docling-core
 Description-Content-Type: text/markdown
 # Docling Core
@@ -51,9 +51,9 @@ Description-Content-Type: text/markdown
 [![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-[![License MIT](https://img.shields.io/github/license/ds4sd/docling-core)](https://opensource.org/licenses/MIT)
+[![License MIT](https://img.shields.io/github/license/docling-project/docling-core)](https://opensource.org/licenses/MIT)
-Docling Core is a library that defines the data types in [Docling](https://github.com/DS4SD/docling), leveraging pydantic models.
+Docling Core is a library that defines the data types in [Docling](https://github.com/docling-project/docling), leveraging pydantic models.
 ## Installation

{docling_core-2.23.0 → docling_core-2.23.2}/README.md RENAMED Viewed

@@ -8,9 +8,9 @@
 [![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-[![License MIT](https://img.shields.io/github/license/ds4sd/docling-core)](https://opensource.org/licenses/MIT)
+[![License MIT](https://img.shields.io/github/license/docling-project/docling-core)](https://opensource.org/licenses/MIT)
-Docling Core is a library that defines the data types in [Docling](https://github.com/DS4SD/docling), leveraging pydantic models.
+Docling Core is a library that defines the data types in [Docling](https://github.com/docling-project/docling), leveraging pydantic models.
 ## Installation

{docling_core-2.23.0 → docling_core-2.23.2}/docling_core/types/doc/document.py RENAMED Viewed

@@ -1548,7 +1548,7 @@ class DoclingDocument(BaseModel):
     _HTML_DEFAULT_HEAD: str = r"""<head>
     <link rel="icon" type="image/png"
-    href="https://ds4sd.github.io/docling/assets/logo.png"/>
+    href="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"/>
     <meta charset="UTF-8">
     <title>
     Powered by Docling
@@ -3051,6 +3051,25 @@ class DoclingDocument(BaseModel):
             """Strip all <...> tags inside the chunk to get the raw text content."""
             return re.sub(r"<.*?>", "", text_chunk, flags=re.DOTALL).strip()
+        def extract_caption(
+            text_chunk: str,
+        ) -> tuple[Optional[TextItem], Optional[BoundingBox]]:
+            """Extract caption text from the chunk."""
+            caption = re.search(r"<caption>(.*?)</caption>", text_chunk)
+            if caption is not None:
+                caption_content = caption.group(1)
+                bbox = extract_bounding_box(caption_content)
+                caption_text = extract_inner_text(caption_content)
+                caption_item = self.add_text(
+                    label=DocItemLabel.CAPTION,
+                    text=caption_text,
+                    parent=None,
+                )
+            else:
+                caption_item = None
+                bbox = None
+            return caption_item, bbox
         def otsl_parse_texts(texts, tokens):
             split_word = TableToken.OTSL_NL.value
             split_row_tokens = [
@@ -3261,16 +3280,24 @@ class DoclingDocument(BaseModel):
                 if tag_name == DocumentToken.OTSL.value:
                     table_data = parse_table_content(full_chunk)
                     bbox = extract_bounding_box(full_chunk) if image else None
+                    caption, caption_bbox = extract_caption(full_chunk)
+                    if caption is not None and caption_bbox is not None:
+                        caption.prov.append(
+                            ProvenanceItem(
+                                bbox=caption_bbox.resize_by_scale(pg_width, pg_height),
+                                charspan=(0, 0),
+                                page_no=page_no,
+                            )
+                        )
                     if bbox:
                         prov = ProvenanceItem(
                             bbox=bbox.resize_by_scale(pg_width, pg_height),
                             charspan=(0, 0),
                             page_no=page_no,
                         )
-                        self.add_table(data=table_data, prov=prov)
+                        self.add_table(data=table_data, prov=prov, caption=caption)
                     else:
-                        self.add_table(data=table_data)
+                        self.add_table(data=table_data, caption=caption)
                 elif tag_name == DocItemLabel.PICTURE:
                     text_caption_content = extract_inner_text(full_chunk)

{docling_core-2.23.0 → docling_core-2.23.2}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-core"
-version = "2.23.0"
+version = "2.23.2"
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 authors = [
@@ -22,8 +22,8 @@ maintainers = [
     "Panos Vagenas <pva@zurich.ibm.com>",
 ]
 readme = "README.md"
-homepage = "https://ds4sd.github.io/"
-repository = "https://github.com/DS4SD/docling-core"
+homepage = "https://github.com/docling-project"
+repository = "https://github.com/docling-project/docling-core"
 keywords = ["docling", "discovery", "etl", "information retrieval", "analytics", "database", "database schema", "schema", "JSON"]
 classifiers=[
     "Development Status :: 5 - Production/Stable",